knitr::opts_chunk$set(echo = TRUE, message = FALSE, warning = FALSE)

library(tidyverse)
library(here)
library(sf)
library(tmap)

# to update packages use `update.packages(ask = FALSE)`

Reading in data

sf_trees <- read_csv(here("data", "sf_trees", "sf_trees.csv"), show_col_types = FALSE) # wont show the column types

Part 1: wrangling and ggplot review

Example 1: Find counts of observations by legal_status & wrangle a bit.

### method 1: `group_by() %>% summarize()
sf_trees %>% 
  group_by(legal_status) %>% 
  summarize(tree_count = n())
## # A tibble: 10 × 2
##    legal_status                 tree_count
##    <chr>                             <int>
##  1 DPW Maintained                   141725
##  2 Landmark tree                        42
##  3 Permitted Site                    39732
##  4 Planning Code 138.1 required        971
##  5 Private                             163
##  6 Property Tree                       316
##  7 Section 143                         230
##  8 Significant Tree                   1648
##  9 Undocumented                       8106
## 10 <NA>                                 54
### method 2: different way plus a few new functions
top_5_status <- sf_trees %>% 
  count(legal_status) %>% 
  drop_na(legal_status) %>% 
  rename(tree_count = n) %>% 
  relocate(tree_count, 1) %>% # reorder columns
  slice_max(tree_count, n =5) %>% # takes top 5 highest values
  arrange(desc(tree_count)) # highest to lowest value sort

Make a graph of the top 5 from above

ggplot(data = top_5_status, aes(x = fct_reorder(legal_status, tree_count), #fct_reorder orders from smallest to largest # of trees
                                y = tree_count)) +
  geom_col(fill = 'darkgreen') +
  labs(x = 'Legal status',
       y = 'Tree count') +
   coord_flip() + #will flip the axis labels so they fit the entire word
  theme_minimal()

Example 2: Only going to keep observations where legal status is “Permitted Site” and caretaker is “MTA”, and store as permitted_data_df

# sf_trees$legal_status %>% unique() # checks for unique values
permitted_data_df <- sf_trees %>% 
  filter(legal_status == "Permitted Site", 
         caretaker == "MTA")

Example 3: Only keep Blackwood Acacia trees, and then only keep columns legal_status, date, latitude. and store as blackwood_acacia_df

blackwood_acacia_df <- sf_trees %>% 
  filter(str_detect(species, 'Blackwood Acacia')) %>% 
  select(legal_status, date, lat = latitude, lon = longitude)

# Make a little graph of locations
ggplot(data = blackwood_acacia_df, aes(x = lon, y = lat)) +
  geom_point(color = "darkgreen")

Example 4: use tidyr::separate() to separate words in a column into two separate columns

sf_trees_map <- sf_trees %>% 
  separate(species, into = c('spp_scientific', 'spp_common'), sep = '::')

Example 5: use tidyr::unite()

ex_5 <- sf_trees %>% 
  unite('id_status', tree_id, legal_status, sep = ' ADDING THIS ')

Part 2: make some maps

Step 1: convert the lat/lon to spatial points, st_as_sf()

blackwood_acacia_sf <- blackwood_acacia_df %>% 
  drop_na(lat, lon) %>% 
  st_as_sf(coords = c('lon', 'lat'))

# we need to tell R what the coordinate reference system is
st_crs(blackwood_acacia_sf) <- 4326 #WGS84

ggplot(data = blackwood_acacia_sf) +
  geom_sf(color = 'darkgreen') +
  theme_minimal()

Read in the SF shapefile and add to map

sf_map <- read_sf(here("data", "sf_map", "tl_2017_06075_roads.shp"))

sf_map_transform <- st_transform(sf_map, 4326)

ggplot(data = sf_map_transform) +
  geom_sf()

Combine the maps!

ggplot() +
  geom_sf(data= sf_map,
          size = 0.1,
          color = "darkgrey") + #will be on the bottom layer 
  geom_sf(data= blackwood_acacia_sf,
          size = 0.5,
          color = "darkgreen") +
  theme_void() +
  labs(title = "Blackwood Acacias in SF")

Now an interactive one!

tmap_mode("view")

tm_shape(blackwood_acacia_sf) + 
  tm_dots()